bev-decider-0.4B：兼容 Jev API 的开源决策模型
开源 0.4B 因果决策模型，基于 Qwen 前 20 层，单次并行前向约 50ms，并提供 Jev 兼容的 /v1/systemone 接口，代码权重数据全开放。
Releasing bev-decider-0.4B: a lightweight causal decision model that is architecturally invariant of input choice order. Its built on the first 20 layers of Qwen. Processes the prompt and choices in one parallel forward pass. Runs superfast at ~50ms even on my 3-yr old mac (no speedups in the demo). This started as for a ed youtube video, but I was having too much fun, so I'm releasing everything. Dataset, code, weights are all open source. The video (full project, start to finish) drops this week! Bev is pip installable and comes with a Jev-compatible /v1/systemone api. You can find benchmark details in the HF model page. :) Github: https://github.com/avbiswas/bev-train Model: https://huggingface.co/avbiswas/bev-decider-0.4B Data: https://huggingface.co/datasets/avbiswas/bev-decision
这条是引用着另一条写的：x.com/neural_avb/status/2103822851359027207